Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    expressions related to making choices and regrets about past decisions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    byn
    -0.16
    uty
    -0.16
     ç¤
    -0.15
    osomal
    -0.15
    ÙĨÙĩ
    -0.14
     Blades
    -0.14
    iet
    -0.14
    ÐĴÑĤ
    -0.13
    iam
    -0.13
    gren
    -0.13
    POSITIVE LOGITS
     cult
    0.18
    los
    0.15
     HQ
    0.14
    erva
    0.14
    stant
    0.14
     Rubio
    0.14
    HQ
    0.14
    aed
    0.14
    apro
    0.14
    ãģľ
    0.14
    Act Density 0.132%

    No Known Activations